Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _marker
    -0.07
    LTR
    -0.07
    个人
    -0.07
    _perc
    -0.07
     def
    -0.07
     вк
    -0.06
     comando
    -0.06
    承
    -0.06
     GET
    -0.06
     방문
    -0.06
    POSITIVE LOGITS
    onitor
    0.07
     lẫn
    0.06
     Uses
    0.06
     Papers
    0.06
     loader
    0.06
    дать
    0.06
    ″
    0.06
    _force
    0.06
    Literal
    0.06
    ESTAMP
    0.06
    Act Density 0.002%

    No Known Activations